© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130742
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    just
    -0.28
    quoise
    -0.26
    chest
    -0.25
    wall
    -0.25
    åıĺæĢģ
    -0.24
    à¹Īา
    -0.24
     Bail
    -0.24
    chains
    -0.23
     Just
    -0.23
    *(-
    -0.23
    POSITIVE LOGITS
    ä¸ŃåĽ½åĪ¶éĢł
    0.25
     kre
    0.24
    IDEO
    0.24
    iore
    0.24
     rode
    0.23
     Yad
    0.23
    oy
    0.23
     plunge
    0.23
     hmm
    0.23
     Tome
    0.23
    Activations Density 0.072%

    No Known Activations

    This feature has no known activations.